maybe more mental health oriented analysis might be useful?

I reverse engineered the dayone2 sqlite database to access my journal entries 😬

Other tasks planned are LLM generated summaries of months and years (tbh still squeamish about sending my entire journal data to openAI but also curious) and statistics on human mentions

Using scores from ModernBERT tuned on sentiment analysis. It's definitely misleading because it the score is the model confidence in the class instead of magnitude of my joy but it makes pretty plots. I wonder if we can turn this into a "rate my day" regression task to give a score between 0 and 1

They definitely captured the spirit of the book!

Leto Artreides role in Dune 4 confirmed

I agree that 80% correctness used to be unacceptable in software

One highlight was losing interpretability when moving from symbolic AI to statistical models - I vaguely remember debugging a RDF based QA system and the biggest issue was almost always out of date / missing knowledge. So yeah I almost always knew what went wrong lol

huh literally just heard of:
Spatially adaptive Computation time
Depth adaptive transformer

point is to estimate difficulty and give model a constraint to try to fit into

Click on notifications and then settings (cog on top right)? That being said I don't have enough followers to verify it works lol

If it can repeatedly attend over the image tokens, yes. Maybe vision models need their “think step by step” moment